You will join the development of an AI product in the field of international law — a high-load multi-agent system where each node requires deep understanding and precise tuning.
In addition to working on the product, you will become an internal expert on AI infrastructure: you will conduct pilots of new technologies, help other teams deploy their experiments, participate in standardizing MLOps approaches, and support common platforms for working with data and models.
What you will do:
- manage Kubernetes infrastructure
- develop and support IaC, CI/CD, and GitOps processes, as well as initiate and conduct pilots (PoC) of new technologies
- configure and maintain messaging, caching, and data storage systems
- implement MLOps / LLMOps practices
- organize centralized monitoring and alerting for all infrastructure and applications
- ensure security and access management: authentication, secrets, network policies, compliance with standards
- deploy AI solutions in a hybrid environment: cloud platforms and on-premise.
We expect you to have:
- DevOps / SRE experience of 3+ years, with at least 2 years with Kubernetes in production: Helm, networking, RBAC, auto-scaling
- deep knowledge of message brokers (Kafka, RabbitMQ): clustering, tuning, Schema Registry
- experience administering PostgreSQL (replication, backups, tuning) and experience with vector/graph databases (Milvus, Neo4j)
- experience building CI/CD using GitLab CI / GitHub Actions and/or Jenkins (writing pipeline scripts in Groovy)
- monitoring and logging: Prometheus, Grafana, Loki
- experience with MLOps (MLflow, Airflow/Prefect) and GPU infrastructure – mandatory for working with LLM
- scripting in Bash/Python, knowledge of Linux, network stack
- configuration of authentication systems (Keycloak or similar).
Will be a plus:
- experience in the financial sector (banks) with high reliability and security requirements
- experience in LegalTech or with systems requiring high data accuracy
- knowledge of OpenShift as an enterprise containerization platform
- experience with inference servers (NVIDIA Triton, Ollama) and LLM deployment
- knowledge of Ansible for configuration automation
- understanding of security standards and experience implementing them
- English language (reading documentation, communicating with the team).
We offer:
- freedom to experiment and implement new technologies
- career growth to Lead DevOps / SRE with real authority, responsibility, and the opportunity to shape engineering culture
- hybrid schedule (2-3 days in the office per week)
- office at Poklonnaya, 3k3
- annual salary review and annual bonus
- over 400 educational programs from SberUniversity for professional and career development
- adaptation program and mentor support at the start
- extended voluntary medical insurance, preferential family insurance, and corporate pension program
- preferential mortgage and lending from Sber
- free SberPrime+ subscription, discounts on products from partner companies.
